论文标题
多米诺显着性指标：通过结构信息改善现有的频道显着性指标
Domino Saliency Metrics: Improving Existing Channel Saliency Metrics with Structural Information
论文作者
论文摘要
通道修剪用于减少卷积神经网络（CNN）中的权重次数。通道修剪去除重量张量的切片，从而使卷积层保持密集。从单层中去除这些重量切片会导致网络层之间的特征图数不匹配。一个简单的解决方案是迫使图层之间的特征图数量通过从后续层中去除重量切片来匹配。在带有分支的DNN中，这种附加的约束变得更加明显，其中需要将多个通道一起整理在一起以保持网络密度。流行的修剪显着性指标并不能考虑具有分支的DNN中产生的结构依赖性。我们建议多米诺骨牌指标（基于现有的渠道显着性指标）来反映这些结构性约束。我们测试了具有分支机构的多个网络上基线通道显着性指标。 Domino显着性指标提高了大多数测试网络的修剪率，在CIFAR-10上，ALEXNET中最多可提高25％。
Channel pruning is used to reduce the number of weights in a Convolutional Neural Network (CNN). Channel pruning removes slices of the weight tensor so that the convolution layer remains dense. The removal of these weight slices from a single layer causes mismatching number of feature maps between layers of the network. A simple solution is to force the number of feature map between layers to match through the removal of weight slices from subsequent layers. This additional constraint becomes more apparent in DNNs with branches where multiple channels need to be pruned together to keep the network dense. Popular pruning saliency metrics do not factor in the structural dependencies that arise in DNNs with branches. We propose Domino metrics (built on existing channel saliency metrics) to reflect these structural constraints. We test Domino saliency metrics against the baseline channel saliency metrics on multiple networks with branches. Domino saliency metrics improved pruning rates in most tested networks and up to 25% in AlexNet on CIFAR-10.
